提出渐进式图域自适应框架，解决大规模分布偏移下的图学习迁移难题。
Gradual Domain Adaptation for Graph Learning
- 基于FGW度量生成保留知识的中间图，构建平滑域演化路径。
- 通过顶点级推进策略提升域间可迁移性，实测性能优于现有方法。
- 理论给出不可计算域距离的上下界，支持灵活优化域结构设计。
现有机器学习研究缺乏能应对大规模分布偏移的图域自适应技术，主要受限于难以模拟源图到目标图的连贯演化过程。为此，本文提出图渐进域自适应（GGDA）框架，通过构建最小信息损失的紧凑域序列来应对该挑战。方法首先在融合格罗莫夫-沃瑟斯坦（Fused Gromov-Wasserstein, FGW）度量下高效生成保持知识的中间图，再基于新型顶点级推进策略，从这些桥接图中构建GGDA域序列，通过选择“邻近”顶点并执行自适应域推进，增强域间可迁移性。理论上，框架为难以计算的域间沃瑟斯坦距离 $W_p(μ_t,μ_{t+1})$ 提供了可实现的上下界，支持其灵活调节以实现最优域构造。在多种迁移场景下的大量实验表明，本框架表现显著优于现有方法。
原文摘要 · Abstract (English)
Existing machine learning literature lacks graph-based domain adaptation techniques capable of handling large distribution shifts, primarily due to the difficulty in simulating a coherent evolutionary path from source to target graph. To meet this challenge, we present a graph gradual domain adaptation (GGDA) framework, which constructs a compact domain sequence that minimizes information loss during adaptation. Our approach starts with an efficient generation of knowledge-preserving intermediate graphs over the Fused Gromov-Wasserstein (FGW) metric. A GGDA domain sequence is then constructed upon this bridging data pool through a novel vertex-based progression, which involves selecting "close" vertices and performing adaptive domain advancement to enhance inter-domain transferability. Theoretically, our framework provides implementable upper and lower bounds for the intractable inter-domain Wasserstein distance, $W_p(μ_t,μ_{t+1})$, enabling its flexible adjustment for optimal domain formation. Extensive experiments across diverse transfer scenarios demonstrate the superior performance of our GGDA framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。